世界模型 - arXivDaily 专题

2304.13426 2023-04-27 cs.LG stat.ML 50%

FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems

Matthieu Blanke, Marc Lelarge

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments Accepted at ICML 2023

2302.12604 2023-04-12 cs.LG cs.AI cs.RO stat.ML 50%

Neural Laplace Control for Continuous-time Delayed Systems

Samuel Holt, Alihan Hüyük, Zhaozhi Qian, Hao Sun, Mihaela van der Schaar

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2303.17984 2023-04-03 cs.MA 50%

Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning

Zifan Wu, Chao Yu, Chen Chen, Jianye Hao, Hankz Hankui Zhuo

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.MA

2201.12243 2023-03-22 cs.LG cs.SY eess.SY 50%

Joint Differentiable Optimization and Verification for Certified Reinforcement Learning

Yixuan Wang, Simon Zhan, Zhilu Wang, Chao Huang, Zhaoran Wang, Zhuoran Yang, Qi Zhu

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments This paper is accepted to International Conference on Cyber-Physical Systems

2210.02181 2023-03-17 cs.LG stat.AP 50%

DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learning

Mengge Du, Yuntian Chen, Dongxiao Zhang

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2002.12435 2023-03-16 cs.LG math.OC stat.ML 50%

Learning in Markov Decision Processes under Constraints

Rahul Singh, Abhishek Gupta, Ness B. Shroff

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Journal ref IEEE Transactions on Control of Network Systems, 31 August 2022

2212.08765 2023-03-08 cs.LG stat.ML 50%

Latent Variable Representation for Reinforcement Learning

Tongzheng Ren, Chenjun Xiao, Tianjun Zhang, Na Li, Zhaoran Wang, Sujay Sanghavi, Dale Schuurmans, Bo Dai

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments ICLR 2023. The first two authors contribute equally. Project Website: https://rlrep.github.io/lvrep/

2303.02189 2023-03-07 stat.ML cs.LG cs.NA math.NA 50%

Interpretable reduced-order modeling with time-scale separation

Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis, Petros Koumoutsakos

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

2303.00599 2023-03-02 cs.LG cs.AI cs.RO 50%

LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning

Firas Al-Hafez, Davide Tateo, Oleg Arenz, Guoping Zhao, Jan Peters

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2110.12658 2023-02-09 cs.LG cs.NA math.NA math.ST stat.ML stat.TH 50%

Operator Shifting for Model-based Policy Evaluation

Xun Tang, Lexing Ying, Yuhua Zhu

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2301.01298 2023-01-18 cs.LG cs.AI cs.RO 50%

Contextual Conservative Q-Learning for Offline Reinforcement Learning

Ke Jiang, Jiayu Yao, Xiaoyang Tan

专题命中模型式强化学习：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments the work is not finished

2209.05408 2022-12-21 cs.LG cs.HC 50%

Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning

Piyush Gupta, Vaibhav Srivastava

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

2209.13413 2022-12-08 cs.LG cs.SY eess.SY q-bio.NC stat.ML 50%

Reinforcement Learning with Non-Exponential Discounting

Matthias Schultheis, Constantin A. Rothkopf, Heinz Koeppl

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments 22 pages, 3 figures, published at 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

2109.06312 2022-12-06 cs.LG stat.ML 50%

Learning-to-defer for sequential medical decision-making under uncertainty

Shalmali Joshi, Sonali Parbhoo, Finale Doshi-Velez

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2210.03137 2022-11-30 cs.LG math.OC 50%

Deep Inventory Management

Dhruv Madeka, Kari Torkkola, Carson Eisenach, Anna Luo, Dean P. Foster, Sham M. Kakade

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2211.08138 2022-11-16 cs.LG cs.RO 50%

Design of Unmanned Air Vehicles Using Transformer Surrogate Models

Adam D. Cobb, Anirban Roy, Daniel Elenius, Susmit Jha

专题命中模型式强化学习：分类 cs.LG、cs.RO；dynamics model(abstract)；simulation model(abstract)

Comments 8 pages, 8 figures

2206.02072 2022-11-02 cs.LG cs.IT math.IT stat.ML 50%

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Dilip Arumugam, Benjamin Van Roy

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments Accepted to Neural Information Processing Systems (NeurIPS) 2022

2206.07681 2022-10-13 cs.LG physics.comp-ph 50%

Learning to Accelerate Partial Differential Equations via Latent Global Evolution

Tailin Wu, Takashi Maruyama, Jure Leskovec

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments NeurIPS 2022; 30 pages, 15 figures

2005.05210 2022-10-10 stat.ML cs.LG 50%

Interpretable Deep Representation Learning from Temporal Multi-view Data

Lin Qiu, Vernon M. Chinchilli, Lin Lin

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Comments Accepted at ACML 2022

2209.15256 2022-10-03 cs.LG cs.CV cs.RO 50%

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

Daesol Cho, Dongseok Shim, H. Jin Kim

专题命中模型式强化学习：分类 cs.LG、cs.CV、cs.RO；dynamics model(abstract)

Comments NeurIPS 2022, first two authors contributed equally

2208.10892 2022-08-29 q-bio.NC cs.LG cs.NE 50%

What deep reinforcement learning tells us about human motor learning and vice-versa

Michele Garibbo, Casimir Ludwig, Nathan Lepora, Laurence Aitchison

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Comments 23 pages, 5 figures

2205.11648 2022-08-18 cs.LG q-bio.NC 50%

Deep Representations for Time-varying Brain Datasets

Sikun Lin, Shuyun Tang, Scott Grafton, Ambuj Singh

专题命中模型式强化学习：latent dynamics(abstract)；分类 cs.LG

Journal ref ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022

2208.06385 2022-08-17 cs.LG cs.SY eess.SY 50%

Low Emission Building Control with Zero-Shot Reinforcement Learning

Scott R. Jeen, Alessandro Abate, Jonathan M. Cullen

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Comments This paper should have been submitted as a replacement for arXiv:2206.14191

2202.11855 2022-07-28 cs.CV cs.LG cs.RO 50%

Learning Multi-Object Dynamics with Compositional Neural Radiance Fields

Danny Driess, Zhiao Huang, Yunzhu Li, Russ Tedrake, Marc Toussaint

专题命中模型式强化学习：分类 cs.LG、cs.CV、cs.RO；dynamics model(abstract)

Comments v3: real robot exp

2009.08111 2022-07-13 cs.AI math.OC q-bio.NC 50%

Reward Maximisation through Discrete Active Inference

Lancelot Da Costa, Noor Sajid, Thomas Parr, Karl Friston, Ryan Smith

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.AI

Comments 18 pages, 3 figures (main text); 37 pages including references and appendix

2206.14846 2022-07-01 cs.LG cs.SI stat.ML 50%

Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization

Kaixuan Huang, Yu Wu, Xuezhou Zhang, Shenyinying Tu, Qingyun Wu, Mengdi Wang, Huazheng Wang

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

2011.07881 2022-06-29 cs.LG 50%

Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning

Sayak Ray Chowdhury, Rafael Oliveira

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

2206.08736 2022-06-20 stat.ML cs.LG 50%

Generalised Policy Improvement with Geometric Policy Composition

Shantanu Thakoor, Mark Rowland, Diana Borsa, Will Dabney, Rémi Munos, André Barreto

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

Comments ICML 2022

2206.01704 2022-06-06 cs.LG cs.SY eess.SY math.OC stat.ML 50%

KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems

Sahin Lale, Yuanyuan Shi, Guannan Qu, Kamyar Azizzadenesheli, Adam Wierman, Anima Anandkumar

专题命中模型式强化学习：model-based RL(abstract)；分类 cs.LG

2007.12291 2022-06-06 cs.LG math.OC stat.ML 50%

Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

专题命中模型式强化学习：model-based reinforcement learning(abstract)；分类 cs.LG

Comments 25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022

1. 模型式强化学习 1124 篇

FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems

Neural Laplace Control for Continuous-time Delayed Systems

Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning

Joint Differentiable Optimization and Verification for Certified Reinforcement Learning

DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learning

Learning in Markov Decision Processes under Constraints

Latent Variable Representation for Reinforcement Learning

Interpretable reduced-order modeling with time-scale separation

LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning

Operator Shifting for Model-based Policy Evaluation

Contextual Conservative Q-Learning for Offline Reinforcement Learning

Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning

Reinforcement Learning with Non-Exponential Discounting

Learning-to-defer for sequential medical decision-making under uncertainty

Deep Inventory Management

Design of Unmanned Air Vehicles Using Transformer Surrogate Models

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Learning to Accelerate Partial Differential Equations via Latent Global Evolution

Interpretable Deep Representation Learning from Temporal Multi-view Data

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

What deep reinforcement learning tells us about human motor learning and vice-versa

Deep Representations for Time-varying Brain Datasets

Low Emission Building Control with Zero-Shot Reinforcement Learning

Learning Multi-Object Dynamics with Compositional Neural Radiance Fields

Reward Maximisation through Discrete Active Inference

Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization

Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning

Generalised Policy Improvement with Geometric Policy Composition

KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems

Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems